© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3800
    Prev
    Next
    INDEX
    Explanations

    words, symbols, and phrases about a product's technical features, medical conditions, financial responsibility, or professional veterinary practices

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mobili
    -1.54
     stabili
    -1.47
     sterili
    -1.35
     immobili
    -1.34
     paraly
    -1.26
     synthe
    -1.20
     bap
    -1.15
     saniti
    -1.14
     norm
    -1.06
     fertili
    -1.04
    POSITIVE LOGITS
     summar
    0.85
     opti
    0.76
     util
    0.74
     coun
    0.71
     nakalista
    0.70
     catal
    0.69
     مرئيه
    0.66
     critic
    0.65
     pinulongan
    0.63
    
    0.62
    Activations Density 4.580%

    No Known Activations